skills$openclaw/zhipu-search
whyhit20052.6k

by whyhit2005

zhipu-search – OpenClaw Skill

zhipu-search is an OpenClaw Skills integration for coding workflows. |

2.6k stars3.4k forksSecurity L1
Updated Feb 7, 2026Created Feb 7, 2026coding

Skill Snapshot

namezhipu-search
description| OpenClaw Skills integration.
ownerwhyhit2005
repositorywhyhit2005/zhipu-web-search
languageMarkdown
licenseMIT
topics
securityL1
installopenclaw add @whyhit2005/zhipu-web-search
last updatedFeb 7, 2026

Maintainer

whyhit2005

whyhit2005

Maintains zhipu-search in the OpenClaw Skills directory.

View GitHub profile
File Explorer
4 files
.
scripts
zhipu_search.py
10.2 KB
_meta.json
288 B
SKILL.md
3.8 KB
SKILL.md

name: zhipu-search description: | 智谱AI网络搜索工具,提供灵活的搜索引擎调用能力。

Use when:

  • 需要搜索网络信息获取最新数据
  • 需要特定搜索引擎(搜狗、夸克、智谱搜索)
  • 需要按时间范围、域名过滤搜索结果
  • 需要控制搜索结果数量和详细程度

智谱搜索 (Zhipu Search)

通过智谱AI API进行网络搜索,支持多种搜索引擎和灵活的参数配置。

快速使用

基础搜索

# 使用默认参数搜索
search_query = "OpenClaw 最新版本"
search_engine = "search_std"

高级搜索(完整参数)

search_query = "人工智能发展趋势"      # 必填,最多70字符
search_engine = "search_pro"          # 必填:search_std/search_pro/search_pro_sogou/search_pro_quark
search_intent = true                  # 可选,默认false,是否进行搜索意图识别
count = 20                            # 可选,默认10,范围1-50
search_domain_filter = "example.com"  # 可选,限定域名白名单
search_recency_filter = "oneWeek"     # 可选:oneDay/oneWeek/oneMonth/oneYear/noLimit
content_size = "high"                 # 可选:medium/high,控制内容详细程度
request_id = "unique-request-id"      # 可选,唯一请求标识
user_id = "user-123456"               # 可选,终端用户ID(6-128字符)

调用方式

方式1:直接调用脚本(推荐)

python scripts/zhipu_search.py \
  --query "搜索内容" \
  --engine search_pro \
  --count 10

方式2:使用OpenClaw工具调用

系统会自动根据需求选择合适的参数调用搜索功能。

API 参数说明

参数类型必填默认值说明
search_querystring-搜索内容,建议≤70字符
search_engineenum-search_std/search_pro/search_pro_sogou/search_pro_quark
search_intentboolean-false是否进行搜索意图识别
countinteger-10返回结果数量,1-50
search_domain_filterstring--限定白名单域名
search_recency_filterenum-noLimitoneDay/oneWeek/oneMonth/oneYear/noLimit
content_sizeenum--medium/high,控制内容长度
request_idstring--唯一请求标识
user_idstring--终端用户ID(6-128字符)

搜索引擎选择指南

引擎适用场景
search_std基础搜索,常规问答
search_pro高阶搜索,需要更精准结果
search_pro_sogou搜狗搜索,国内内容
search_pro_quark夸克搜索,特定场景

返回结果结构

{
  "id": "task-id",
  "created": 1704067200,
  "request_id": "request-id",
  "search_intent": [
    {
      "query": "原始搜索query",
      "intent": "SEARCH_ALL",
      "keywords": "改写后的关键词"
    }
  ],
  "search_result": [
    {
      "title": "标题",
      "content": "内容摘要",
      "link": "结果链接",
      "media": "网站名称",
      "icon": "网站图标",
      "refer": "角标序号",
      "publish_date": "发布时间"
    }
  ]
}

环境要求

  • 环境变量 ZHIPU_API_KEY 必须已配置
  • Python 3.7+
  • requests 库

注意事项

  1. search_query 建议控制在70字符以内
  2. search_pro_sogou 的 count 必须是 10/20/30/40/50 之一
  3. user_id 如果提供,长度必须在6-128字符之间
  4. 搜索意图识别会增加响应时间,但能提升搜索结果相关性
README.md

No README available.

Permissions & Security

Security level L1: Low-risk skills with minimal permissions. Review inputs and outputs before running in production.

Requirements

  • OpenClaw CLI installed and configured.
  • Language: Markdown
  • License: MIT
  • Topics:

FAQ

How do I install zhipu-search?

Run openclaw add @whyhit2005/zhipu-web-search in your terminal. This installs zhipu-search into your OpenClaw Skills catalog.

Does this skill run locally or in the cloud?

OpenClaw Skills execute locally by default. Review the SKILL.md and permissions before running any skill.

Where can I verify the source code?

The source repository is available at https://github.com/openclaw/skills/tree/main/skills/whyhit2005/zhipu-web-search. Review commits and README documentation before installing.